Related papers: DEAL: Data-Efficient Adversarial Learning for High…

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion…

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…

The phenomenon of adversarial examples illustrates one of the most basic vulnerabilities of deep neural networks. Among the variety of techniques introduced to surmount this inherent weakness, adversarial training has emerged as the most…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

In autonomous driving, thermal image semantic segmentation has emerged as a critical research area, owing to its ability to provide robust scene understanding under adverse visual conditions. In particular, unsupervised domain adaptation…

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that…

Neural network-based approaches can achieve high accuracy in various medical image segmentation tasks. However, they generally require large labelled datasets for supervised learning. Acquiring and manually labelling a large medical dataset…

Image normalization is a critical step in medical imaging. This step is often done on a per-dataset basis, preventing current segmentation algorithms from the full potential of exploiting jointly normalized information across multiple…

Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…

Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural…

Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for…

Automatic fall detection is a vital technology for ensuring the health and safety of people. Home-based camera systems for fall detection often put people's privacy at risk. Thermal cameras can partially or fully obfuscate facial features,…

Autonomous systems rely on sensors to estimate the environment around them. However, cameras, LiDARs, and RADARs have their own limitations. In nighttime or degraded environments such as fog, mist, or dust, thermal cameras can provide…

Understanding the thermal behavior of additive manufacturing (AM) processes is crucial for enhancing the quality control and enabling customized process design. Most purely physics-based computational models suffer from intensive…

We present a novel adversarial distortion learning (ADL) for denoising two- and three-dimensional (2D/3D) biomedical image data. The proposed ADL consists of two auto-encoders: a denoiser and a discriminator. The denoiser removes noise from…

Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images and the limited computation resources in practical applications. Recent research on…

Ultrasound simulation based on ray tracing enables the synthesis of highly realistic images. It can provide an interactive environment for training sonographers as an educational tool. However, due to high computational demand, there is a…

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…

Federated learning struggles with their heavy energy footprint on battery-powered devices. The learning process keeps all devices awake while draining expensive battery power to train a shared model collaboratively, yet it may still leak…

Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms. Current segmentation models are trained and…